Introduction

This is the documentation of the npfl138 package used on the Deep Learning course NPFL138.

The main class in the npfl138 package is the TrainableModule, which provides:

• high-level training, evaluation, and prediction API, including automatic device management;
• serialization and deserialization of weights (optionally including the optimizer) and module options.
• automatic logging via various loggers,
• easy profiling support.

The TransformedDataset class allows applying both per-example and per-batch transformation functions on a given dataset, and simplifies the creation of a corresponding dataloader (in a multi-GPU setting if required).

Furthermore, the package contains a collection of losses and metrics; however, losses from PyTorch and metrics from torchmetrics can also be used directly.

Finally, several utilities are provided, including a Vocabulary class for converting between strings and their indices.

The npfl138 version

__version__ = '2526.3.0'